A healthcare company specializing in artificial intelligence has claimed that its software can identify the extent of prostate cancer more accurately than medical professionals.
Avenda Health conducted a study involving ten doctors, each evaluating 50 prostate cancer cases. The results revealed that the AI software, known as Unfold AI, achieved an accuracy rate of 84.7% in cancer detection. In comparison, the physicians’ assessments varied, with accuracy rates between 67.2% and 75.9%.
The study was conducted in collaboration with UCLA Health and published in the Journal of Urology. It also highlighted that when AI was utilized for cancer contouring, estimates of tumor size were 45 times more accurate and consistent compared to assessments made without AI support.
Shyam Natarajan, an assistant adjunct professor at UCLA and the study’s senior author, noted that AI assistance leads to both improved accuracy and consistency among doctors, which means increased consensus in their evaluations.
Traditionally, doctors rely on MRIs to gauge tumor size; however, some tumors can be “MRI-invisible,” stated Dr. Wayne Brisbane, an assistant professor at the David Geffen School of Medicine at UCLA. In these cases, AI provides valuable assistance where MRIs may fall short.
Dr. Brisbane emphasized that incorporating AI into cancer treatment could enhance personalized care for patients, allowing for treatments that are better suited to individual needs and potentially more effective in combating the disease. He remarked that AI has the potential to outperform human capabilities.
Avenda Health’s CEO, Dr. Shyam Natarajan, expressed that it is encouraging for healthcare providers to see such innovations validated through research and acknowledged by the American Medical Association.
According to the American Cancer Society, approximately 1 in 8 men will be diagnosed with prostate cancer during their lifetime, and 1 in 44 men will succumb to the illness. It is projected that there will be 299,010 new prostate cancer cases in the US this year, with an estimated 35,250 deaths attributed to the disease.